Business Time Sampling Scheme and Its Application

We propose a new method to implement the Business Time Sampling (BTS) scheme for high-frequency financial data using a time-transformation function. The sampled BTS returns have approximately equal volatility with a target average sampling frequency. We investigate the semi-martingale property of the BTS returns and find that the iid Gaussian distribution assumption describes the BTS returns better than returns obtained from the Calendar Time and Tick Time sampling schemes. We propose a modified ACDICV estimate (Tse and Yang (2012)) of intraday volatility based on the BTS methodology and find that our method has superior performance over the Realized Kernel estimate and Tse and Yang’s (2012) estimate based on sampling by price events.

Click here to download paper.